© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207454
    Prev
    Next
    INDEX
    Explanations

    terraced hills and slopes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     আক্রমন
    0.49
     Balliye
    0.46
    軧
    0.46
     విషయ
    0.44
     transformasi
    0.43
    ૄ
    0.43
    愘
    0.43
     Ouvrard
    0.42
     আউট
    0.42
     prawns
    0.42
    POSITIVE LOGITS
    ong
    0.45
    وبت
    0.44
     reg
    0.41
    cence
    0.40
     bure
    0.39
    ρ
    0.38
    ̢
    0.38
    ="
    0.38
    веси
    0.38
    stream
    0.38
    Activations Density 0.000%

    No Known Activations